© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 5052
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or systemic documentation

    oai_token-act-pair · gpt-3.5-turbo

    references to moral and ethical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     metic
    -1.00
     oun
    -0.88
     Zeit
    -0.84
     Axel
    -0.82
     GP
    -0.82
     wrinkles
    -0.81
     Polk
    -0.80
     coat
    -0.79
     tasting
    -0.79
     Qi
    -0.78
    POSITIVE LOGITS
    subject
    1.52
    actual
    1.51
    nob
    1.50
    reality
    1.49
    traditional
    1.48
    other
    1.47
    extremely
    1.46
    commit
    1.46
    hard
    1.46
    notice
    1.46
    Activations Density 0.177%

    No Known Activations